CONF gangadhar:grazBCI2008:2008/IDIAP Recognition of Anticipatory Behavior from Human EEG Garipelli, Gangadhar Chavarriaga, Ricardo Millán, José del R. EXTERNAL http://publications.idiap.ch/attachments/papers/2008/gangadhar-grazBCI2008-2008.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/gangadhar:rr08-52 Related documents In proceedings, 4th Intl. Brain-Computer Interface Workshop and Training Course 2008 IDIAP-RR 08-52 Anticipation increases the efficiency of a daily task by partial advance activation of neural substrates involved in it. Single trial recognition of this activation can be exploited for a novel anticipation based Brain Computer Interface (BCI). In the current work we compare different methods for the recognition of Electroencephalogram (EEG) correlates of this activation on single trials as a first step towards building such a BCI. To do so, we recorded EEG from 9 subjects performing a classical Contingent Negative Variation (CNV) paradigm (usually reported for studying anticipatory behavior in neurophysiological experiments) with GO and NOGO conditions. We first compare classification accuracies with features such as Least Square fitting Line (LSFL) parameters and Least Square Fitting Polynomial (LSFP) coefficients using a Quadratic Discriminant Analysis (QDA) classifier. We then test the best features with complex classifiers such as Gaussian Mixture Models (GMMs) and Support Vector Machines (SVMs). REPORT gangadhar:rr08-52/IDIAP Recognition of Anticipatory Behavior from Human EEG Garipelli, Gangadhar Chavarriaga, Ricardo Millán, José del R. EXTERNAL http://publications.idiap.ch/attachments/reports/2008/gangadhar-idiap-rr-08-52.pdf PUBLIC Idiap-RR-52-2008 2008 IDIAP Published in In proceedings, 4 th International Brain-Computer Interface Workshop and Training Course 2008. Anticipation increases the efficiency of a daily task by partial advance activation of neural substrates involved in it. Single trial recognition of this activation can be exploited for a novel anticipation based Brain Computer Interface (BCI). In the current work we compare different methods for the recognition of Electroencephalogram (EEG) correlates of this activation on single trials as a first step towards building such a BCI. To do so, we recorded EEG from 9 subjects performing a classical Contingent Negative Variation (CNV) paradigm (usually reported for studying anticipatory behavior in neurophysiological experiments) with GO and NOGO conditions. We first compare classification accuracies with features such as Least Square fitting Line (LSFL) parameters and Least Square Fitting Polynomial (LSFP) coefficients using a Quadratic Discriminant Analysis (QDA) classifier. We then test the best features with complex classifiers such as Gaussian Mixture Models (GMMs) and Support Vector Machines (SVMs).